Fusion model of wavelet transform and adaptive neuro fuzzy inference system for stock market prediction

Abstract

Stock market prediction is one of the most important financial subjects that have drawn researchers’ attention for many years. Several factors affecting the stock market make stock market forecasting highly complicated and a difficult task. The successful prediction of a stock market may promise attractive benefits. Various data mining methods such as artificial neural network (ANN), fuzzy system (FS), and adaptive neuro-fuzzy inference system (ANFIS) etc are being widely used for predicting stock prices. The goal of this paper is to find out an efficient soft computing technique for stock prediction. In this paper, time series prediction model of closing price via fusion of wavelet-adaptive network-based fuzzy inference system (WANFIS) is formulated, which is capable of predicting stock market. The data used in this study were collected from the internet sources. The fusion forecasting model uses the discrete wavelet transform (DWT) to decompose the financial time series data. The obtained approximation and detailed coefficients after decomposition of the original time series data are used as input variables of ANFIS to forecast the closing stock prices. The proposed model is applied on four different companies’ previous data such as opening price, lowest price, highest price and total volume share traded. The day end closing price of stock is the outcome of WANFIS model. Numerical illustration is provided to demonstrate the efficiency of the proposed model and is compared with the existing techniques namely ANN and hybrid of ANN and wavelet to prove its effectiveness. The experimental results reveal that the proposed fusion model achieves better forecasting accuracy than either of the models used separately. From the results, it is suggested that the fusion model WANFIS provides a promising alternative for stock market prediction and can be a useful tool for practitioners and economists dealing with the prediction of stock market.